USC Researchers Present at NeurIPS 2020

| December 4, 2020

Topics include privacy-preserving collaborative machine learning, transparency in state-of-the-art prediction models and data-driven algorithm design for large-scale combinatorial optimization problems.


USC researchers will present 19 papers at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), a virtual-only event running Dec. 5 through 12.

Launched in 1986, the annual machine learning and computational neuroscience conference has evolved into one of the world’s leading AI gatherings. With 38% more paper submissions than 2019, this has been another record-breaking year for NeurIPS. A total of 1,903 papers were accepted, compared to 1,428 last year. The NeurIPS 2020 paper acceptance rate is 20.1 percent — slightly lower than last year’s 21 percent.

USC Papers:

How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions

Michael Tsang (USC)*; Sirisha Rambhatla (USC); Yan Liu (USC)

Theoretical Insights into Multiclass Classification: A High-dimensional Asymptotic View

Christos Thrampoulidis (University of California, Santa Barbara)*; Samet Oymak (University of California, Riverside); Mahdi Soltanolkotabi (USC)

Bias No More: High-Probability Data-Dependent Regret Bounds for Adversarial Bandits and MDPs

Chung-Wei Lee (USC); Haipeng Luo (USC)*; Chen-Yu Wei (USC); Mengxiao Zhang (USC)

Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition

Tiancheng Jin (USC)*; Haipeng Luo (USC)

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Jinhyun So (USC)*; Basak Guler (USC); Salman Avestimehr (USC)

Classification with Valid and Adaptive Coverage

Yaniv Romano (Stanford University)*; Matteo Sesia (USC); Emmanuel Candes (Stanford University)

Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems

Songtao Lu (IBM Research)*; Meisam Razaviyayn (USC); Bo Yang (University of Minnesota); Kejun Huang (University of Florida); Mingyi Hong (University of Minnesota)

A General Large Neighborhood Search Framework for Solving Integer Linear Programs

Jialin Song (Caltech)*; Ravi Lanka (Jet Propulsion Laboratory); Yisong Yue (Caltech); Bistra Dilkina (USC)

Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition

Lin Chen (University of California, Berkeley)*; Qian Yu (USC); Hannah Lawrence (Flatiron Institute); Amin Karbasi (Yale)

Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge

Chaoyang He (USC)*; Murali Annavaram (USC); Salman Avestimehr (USC)

Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

Yi Zhou (USC)*; Chenglei Wu (Facebook Reality Labs); Zimo Li (USC); Chen Cao (Facebook Reality Labs); Yuting Ye (Facebook Reality Labs); Jason Saragih (Facebook); Hao Li (Pinscreen/USC/USC ICT); Yaser Sheikh (Facebook Reality Labs)

Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes

Dongsheng Ding (USC)*; Kaiqing Zhang (University of Illinois at Urbana-Champaign (UIUC)); Tamer Basar (University of Illinois at Urbana-Champaign); Mihailo Jovanovic (USC)

Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss

Shuang Qiu (University of Michigan)*; Xiaohan Wei (USC); Zhuoran Yang (Princeton); Jieping Ye (Didi Chuxing & University of Michigan); Zhaoran Wang (Northwestern U)

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Karl Pertsch (USC)*; Oleh Rybkin (University of Pennsylvania); Frederik Ebert (UC Berkeley); Shenghao Zhou (University of Pennsylvania); Dinesh Jayaraman (University of Pennsylvania); Chelsea Finn (Stanford); Sergey Levine (UC Berkeley)

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

Vu Nguyen (Amazon Research Australia)*; Vaden Masrani (University of British Columbia); Rob Brekelmans (USC Information Sciences Institute); Michael A.  Osborne (University of Oxford); Frank Wood (University of British Columbia)

Comparator-Adaptive Convex Bandits

Dirk van der Hoeven (Leiden University)*; Ashok Cutkosky (Google Research); Haipeng Luo (USC)

Multi-agent Trajectory Prediction with Fuzzy Query Attention

Nitin Kamra (USC)*; Hao Zhu (Peking University); Dweep Kumarbhai Trivedi (USC); Ming Zhang (Peking University); Yan Liu (USC)

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Seyed Mohammadreza Mousavi Kalan (USC)*; Zalan Fabian (USC); Salman Avestimehr (USC); Mahdi Soltanolkotabi (USC)

Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning

Sirisha Rambhatla (USC)*; Xingguo Li (Princeton University); Jarvis Haupt (University of Minnesota)

Published on December 4th, 2020

Last updated on May 16th, 2024

Share This Story